Geoffrey Irving on philosophy depth and medium-term governance progress
geoffreyirving · x · 2026-08-27
Geoffrey Irving responds to Wei Dai's pushback on why they aren't focusing solely on broadcasting negative results. Key points:
- Complexity Model: Argues PSPACE models philosophical argument trees better than EXPTIME, countering the underestimation of depth.
- Medium-term Narrative: With governance success, methods can screen off direct utility attainment (e.g., blocking agents from incomprehensible equilibria via simplified single-agent alignment).
- Broadcasting: Discusses the agreement on broadcasting negative results.
More from AGI Musings
- OpenAI targets internal AGI by end of 2026: TIME report — imjustnewatai · 2026-08-27
- Continual Learning is AI's Holy Grail: Fluid intelligence will enable the next capability leap — daniel_mac8 · 2026-08-27
- Game 'Lord of Tokens': Simulating the Full AI Startup Chain — Charlotte1309 · 2026-08-27
- AI Frees Human Time: Community Experiments Rehearse the Future — cccalum · 2026-08-27
- AI is an Intellectual Revolution, Not Just Technological — JoshuaJBouw · 2026-08-27
- Funding the Commons Forum to Address Wealth Distribution in the AI Era — omojumiller · 2026-08-27